Model Merging

MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning ICCV 2025 Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity ICLR 2025 Model Merging for Knowledge Editing ACL 2025 Model Merging to Maintain Language-Only Performance in Developmentally Plausible Multimodal Models EMNLP 2025 Model merging with SVD to tie the Knots ICLR 2025 MoFE: Mixture of Frozen Experts Architecture NAACL 2025 MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task Learning ACL 2025 MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection ICLR 2025 M-Ped: Multi-Prompt Ensemble Decoding for Large Language Models EMNLP 2025 MSA at BEA 2025 Shared Task: Disagreement-Aware Instruction Tuning for Multi-Dimensional Evaluation of LLMs as Math Tutors ACL 2025 Multi-concept Model Immunization through Differentiable Model Merging AAAI 2025 Multi-Modality Expansion and Retention for LLMs through Parameter Merging and Decoupling ACL 2025 Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models ACL 2025 Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer ACL 2025 NeuronMerge: Merging Models via Functional Neuron Groups ACL 2025 Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance EMNLP 2025 Octopus: Towards Building the Arabic Speech LLM Suite EMNLP 2025 One for All: Update Parameterized Knowledge Across Multiple Models with Once Edit ACL 2025 On Multilingual Encoder Language Model Compression for Low-Resource Languages IJCNLP 2025 Optimize Incompatible Parameters Through Compatibility-aware Knowledge Integration AAAI 2025 ORAL: Prompting Your Large-Scale LoRAs via Conditional Recurrent Diffusion EMNLP 2025 PaCA: Partial Connection Adaptation for Efficient Fine-Tuning ICLR 2025 ParamΔ for Direct Mixing: Post-Train Large Language Model At Zero Cost ICLR 2025 PaRa: Personalizing Text-to-Image Diffusion via Parameter Rank Reduction ICLR 2025 Personality Vector: Modulating Personality of Large Language Models by Model Merging EMNLP 2025